#concurrent-multi-model

#concurrent-multi-model

I was always a tinkerer, I guess. I grew up in the age where computers were not ubiquitous or common. An experience as a kid was instrumental in how my career happened.

The new capabilities center on two integrated components: the Dynamo Planner Profiler and the SLO-based Dynamo Planner. These tools work together to solve the "rate matching" challenge in disaggregated serving. The teams use this term when they split inference workloads. They separate prefill operations, which process the input context, from decode operations that generate output tokens. These tasks run on different GPU pools. Without the right tools, teams spend a lot of time determining the optimal GPU allocation for these phases.

An observability control plane isn't just a dashboard. It's the operational authority system. It defines alert rules, routing, ownership, escalation policy, and notification endpoints. When that layer is wrong, the impact is immediate. The wrong team gets paged. The right team never hears about the incident. Your service level indicators look clean while production burns.

What happens under the hood? How is the search engine able to take that simple query, look for images in the billions, trillions of images that are available online? How is it able to find this one or similar photos from all that? Usually, there is an embedding model that is doing this work behind the hood.

When I manage infrastructure for major events (whether it is the Olympics, a Premier League match or a season finale) I am dealing with a "thundering herd" problem that few systems ever face. Millions of users log in, browse and hit "play" within the same three-minute window. But this challenge isn't unique to media. It is the same nightmare that keeps e-commerce CTOs awake before Black Friday or financial systems architects up during a market crash. The fundamental problem is always the same: How do you survive when demand exceeds capacity by an order of magnitude?

The main advantage of going the Multi-Cloud way is that organizations can "put their eggs in different baskets" and be more versatile in their approach to how they do things. For example, they can mix it up and opt for a cloud-based Platform-as-a-Service (PaaS) solution when it comes to the database, while going the Software-as-a-Service (SaaS) route for their application endeavors.

Steve Yegge thinks he has the answer. The veteran engineer - 40+ years at Amazon, Google and Sourcegraph - spent the second half of 2025 building Gas Town, an open-source orchestration system that coordinates 20 to 30 Claude Code instances working in parallel on the same codebase. He describes it as "Kubernetes for AI coding agents." The comparison isn't just marketing. It's architecturally accurate.